StyleGAN2 + ADA

Reported on 3 benchmarks across 2 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Image GenerationonFFHQ 256 x 256
FID· 2020-06-11
3.62
best: 1.68 (StyleSAN-XL)
SOTA
Training Generative Adversarial Networks with Limited Data arXiv:2006.06676
Image GenerationonArtBench-10 (32x32)
FID· 2020-06-11
2.625
SOTA
Training Generative Adversarial Networks with Limited Data arXiv:2006.06676

Computer Vision1 result

Conditional Image GenerationonArtBench-10 (32x32)
FID· 2020-06-11
2.625
SOTA
Training Generative Adversarial Networks with Limited Data arXiv:2006.06676